Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    typescript code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    1.18
    если
    1.16
    Если
    1.14
     Если
    1.13
     fields
    1.13
    aczego
    1.11
     jeżeli
    1.11
    ,
    1.11
    ного
    1.10
    يں
    1.10
    POSITIVE LOGITS
    はじ
    1.41
    ل
    1.39
     compét
    1.34
     Cait
    1.32
    asını
    1.32
     amulet
    1.32
     dział
    1.31
     étudi
    1.31
    то
    1.30
     dane
    1.30
    Act Density 0.002%

    No Known Activations